Computer Vision is a set of algorithms that are developed to be able to interpret information that are derived from a digital image or video. Human vision is able to recognize items based on past interactions with such items and its traits. Computer vision defers from human vision in that it doesn’t see things as a whole, but rather a collection of pixels, it is due to this that algorithms have to be developed to help.
For example, using pixel and color and brightness, it is able to detect motion. Also unlike human vision, computer vision is not a thing that can be widely used, it is an umbrella term for different algorithms that possesses the functions of tracking, or understanding information from images or videos.
Computer vision’s ability to track and focus on objects allows interactivity between human and art pieces. It allows for artists to create pieces that are able to have a layer of interactivity that doesn’t even need the user to be touching anything physical. As an example, in a project for a different class, using simple computer vision code, we were able to produce a program that detects hand gestures, which then translates to Morse Code.